Search

This study aimed to evaluate the ability of the pix2pix generative adversarial network (GAN) to improve the image quality of low-count dedicated breast positron emission tomography (dbPET). Pairs of full- and low-count dbPET images were collected from 49 breasts. An image synthesis model was constructed using pix2pix GAN for each acquisition time with training (3776 pairs from 16 breasts) and validation data (1652 pairs from 7 breasts). Test data included dbPET images synthesized by our model from 26 breasts with short acquisition times. Two breast radiologists visually compared the overall image quality of the original and synthesized images derived from the short-acquisition time data (scores of 1–5). Further quantitative evaluation was performed using a peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In the visual evaluation, both readers revealed an average score of >3 for all images. The quantitative evaluation revealed significantly higher SSIM (p < 0.01) and PSNR (p < 0.01) for 26 s synthetic images and higher PSNR for 52 s images (p < 0.01) than for the original images. Our model improved the quality of low-count time dbPET synthetic images, with a more significant effect on images with lower counts.

Background and objectives: In the treatment of the special type of breast cancer (STBC), the choice of chemotherapeutic agents is often based on the characteristic features of the histological type. On the other hand, the surgical strategy is usually determined by the tumor size and presence of lymph node metastasis, and the indication for immediate reconstruction is rarely discussed based on the histological type. The prognoses of STBC and invasive ductal carcinoma of the breast (IDC) patients who underwent subcutaneous mastectomy (SCM) with immediate reconstruction at our institution were compared. Materials and Methods: A total of 254 patients with SCM with immediate reconstruction from 1998 to 2018 were included; their tumor diameter or induration was less than 25 mm, and it was not in close proximity to the skin. Preoperative chemotherapy and non-invasive cancer cases were excluded. Results: The number of patients was 166 for skin-sparing mastectomy (SSM) and 88 for nipple-sparing mastectomy (NSM). The reconstructive techniques were deep inferior epigastric artery perforator flap (DIEP) reconstruction in 43 cases, latissimus dorsi flap reconstruction (LDflap) in 63 cases, tissue expander (TE) in 117 cases, and transverse rectus abdominis myocutaneous flap/vertical rectus abdominis myocutaneous flap (TRAM/VRAM) reconstruction in 31 cases. The histological types of breast cancer were 211 IDC and 43 STBC; 17 were mucinous carcinoma (MUC), 17 were invasive lobular carcinoma (ILC), 6 were apocrine carcinoma, 1 was tubular carcinoma, and 2 were invasive micropapillary carcinoma. There was no difference in local recurrence or disease-free survival (LRFS, DFS) between IDC and STBC, and overall survival (OS) was significantly longer in STBC. OS was better in the STBC group because SCM with immediate reconstruction was performed for STBC, which is a histological type with a relatively good prognosis. Highly malignant histological types, such as squamous cell carcinoma or metaplastic carcinoma, were totally absent in this study. Conclusions: The indications for SCM with immediate reconstruction for relatively common STBCs such as MUC and ILC can be the same as for IDC.

Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future.